Remote job
QA Engineer (AI & Feature Testing)
Job details
About this role
Role overview Own quality assurance for web, mobile, and API features on a personal finance platform, including components that use AI language models. The work calls for choosing between conventional pass/fail testing and evaluation methods suited to probabilistic outputs, then communicating findings clearly to an internationally distributed team working across Latin American hours.
Responsibilities - Plan and run tests for both standard software features and AI-enabled behavior, selecting methods that fit the expected outcome. - Translate requirements, user journeys, and process documentation into test plans, cases, and scripts. - Manually test features across platforms and verify fixes. - Report defects in detail, including unexpected model responses, hallucinations, and performance regressions. - Help develop and share quality practices for emerging AI technologies; build deep knowledge of core systems and business processes. - Work closely with engineering, IT, and functional partners.
Requirements - Five to seven years of testing experience across web, mobile, and APIs. - Production experience with Playwright. - Practical experience testing AI or LLM features for accuracy, relevance, edge cases, adversarial inputs, and safety. - Understanding of deterministic testing and AI evaluation methods, including human review, metrics, benchmark datasets, and semantic evaluation. - Familiarity with web and mobile development lifecycles, including iOS and Android. - Experience with integration, regression, performance or load testing, and user acceptance testing; skill with browser developer tools and log monitoring. - Advanced Jira and Confluence proficiency and experience with test management systems.
Nice to have - Experience with Charles Proxy or Fiddler, Xcode or ADB logs, or financial services and fintech. - A computer science degree or equivalent background.
Benefits and work setup - Opportunity to contribute to applied AI projects in a global, inclusive team with an emphasis on continuous learning and responsible AI.